2 papers
cs.CR2026
CNT: Safety-oriented Function Reuse across LLMs via Cross-Model Neuron Transfer
Yue Zhao, Yujia Gong, Ruigang Liang +4
The widespread deployment of large language models (LLMs) calls for post-hoc methods that can flexibly adapt models to evolving safety requirements. Meanwhile, the rapidly expandin…
cs.CL2026
CtrlRAG: Black-box Document Poisoning Attacks for Retrieval-Augmented Generation of Large Language Models
Runqi Sui
Retrieval-Augmented Generation (RAG) systems enhance response credibility and traceability by displaying reference contexts, but this transparency simultaneously introduces a novel…